INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.06

2:0.08

3:0.10

4:0.08

5:0.07

6:0.09

7:0.07

8:0.10

9:0.07

10:0.07

11:0.08

Negative Logits

aleb

-1.66

 fixtures

-1.64

 illegally

-1.64

 injuries

-1.54

 timely

-1.54

 medically

-1.48

BW

-1.47

 setbacks

-1.46

 leaked

-1.46

 professionally

-1.46

POSITIVE LOGITS

lisher

1.98

 "$:/

1.87

ellen

1.79

ordes

1.74

egal

1.74

Higher

1.74

Democratic

1.71

ⓘ

1.70

izabeth

1.65

Commerce

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.